The secure steganography for hiding images via GAN

被引:22
作者
Fu, Zhangjie [1 ,2 ]
Wang, Fan [1 ]
Cheng, Xu [1 ]
机构
[1] Nanjing Univ Informat Sci & Technol, Dept Comp & Software, Nanjing 210044, Peoples R China
[2] Pengcheng Lab, Shenzhen 518000, Peoples R China
基金
中国国家自然科学基金;
关键词
Steganography; Information hiding; Generative adversarial networks; Deep learning; STEGANALYSIS;
D O I
10.1186/s13640-020-00534-2
中图分类号
TM [电工技术]; TN [电子技术、通信技术];
学科分类号
0808 ; 0809 ;
摘要
Steganography is one of the important methods in the field of information hiding, which is the technique of hiding secret data within an ordinary file or message in order to avoid the detection of steganalysis models and human eyes. In recent years, many scholars have applied various deep learning networks to the field of steganalysis to improve the accuracy of detection. The rapid improvement of the accuracy of steganalysis models has caused a huge threat to the security of steganography. In addition, another important factor that limits the security of steganography is capacity. The larger the capacity, the worse and more unnatural the visual quality of carrier images after embedded. Therefore, this paper proposes a steganography model-HIGAN, which constructs the encoding network composed of residual blocks to hide the color secret image into another color image of the same size to output a lower distortion and higher visual quality steganographic image. Moreover, it utilizes the adversarial training between the encoder-decoder network and the steganalysis model to improve the ability to resist the detection of steganalysis models based on deep learning. The experimental results show that our proposed model is achievable and effective. Compared with the previous steganography model for hiding color images based on deep learning, the steganography model in this article could achieve steganographic images with higher visual quality and stronger security.
引用
收藏
页数:18
相关论文
共 29 条
[1]  
[Anonymous], 2016, Generative adversarial networks for image steganography
[2]  
Baluja S, 2017, ADV NEUR IN, V30
[3]   Deep Residual Network for Steganalysis of Digital Images [J].
Boroumand, Mehdi ;
Chen, Mo ;
Fridrich, Jessica .
IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY, 2019, 14 (05) :1181-1193
[4]  
Denemark T, 2014, IEEE INT WORKS INFOR, P48, DOI 10.1109/WIFS.2014.7084302
[5]  
Deng J, 2009, PROC CVPR IEEE, P248, DOI 10.1109/CVPRW.2009.5206848
[6]   Reversible Image Steganography Scheme Based on a U-Net Structure [J].
Duan, Xintao ;
Jia, Kai ;
Li, Baoxia ;
Guo, Daidou ;
Zhang, En ;
Qin, Chuan .
IEEE ACCESS, 2019, 7 :9314-9323
[7]   Coverless Steganography for Digital Images Based on a Generative Model [J].
Duan, Xintao ;
Song, Haoxian ;
Qin, Chuan ;
Khan, Muhammad Khurram .
CMC-COMPUTERS MATERIALS & CONTINUA, 2018, 55 (03) :483-493
[8]   Rich Models for Steganalysis of Digital Images [J].
Fridrich, Jessica ;
Kodovsky, Jan .
IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY, 2012, 7 (03) :868-882
[9]  
Goodfellow I., 2019, GENERATIVE ADVERSARI, P723
[10]  
Hayes J, 2017, ADV NEUR IN, V30